agentleFS
Fili999Fili999/ai-hub/skills/own/report-pdf/SKILL.md

report-pdf

Skill2 starsChanged 4 days agoMITView on GitHub

Generate a comprehensive, detailed, and elegant PDF report reconstructing the entire project journey from concept through development, architecture, challenges and solutions, organized into chapters, milestones, and key highlights. Styled with brand assets (colors, Space Grotesk or Montserrat fonts, logo, slogan) and strategic typographic highlights.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user asks for a comprehensive, executive, or technical project report in PDF format.

    line 15
  2. Distinctive:

    When a polished layout is required, branded with project logo, colors, and modern typography (Space Grotesk, Montserrat).

    line 18
  3. Very specific:

    Check for brand kit in brand/brand-kit.json, brand/, ui/public/brand/, or repository assets.

    line 39
  4. Distinctive:

    Use the template in Report Template or include the essential CSS block:

    line 56
  5. Very specific:

    Always run the skill's cross-platform Node.js script:

    line 74
  6. Distinctive:

    Verify that the generated PDF file exists, is readable, and has a non-zero file size.

    line 79
  7. Distinctive:

    Source fidelity: Do not fabricate decisions, issues, or dates not grounded in real commits or documentation.

    line 95
  8. Very specific:

    Page break controls: Ensure long tables and milestone blocks avoid splitting across pages via page-break-inside: avoid.

    line 96

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Report PDF

Generates a publication-quality PDF document that reconstructs the complete project trajectory: the genesis of the original concept, motivation and the "why", technical architecture, development phases, chronological milestones, encountered challenges and their solutions, up to the future roadmap. Integrates visual brand assets (logo, slogan, color palette from brand/brand-kit.json) and respects typographic design choices (Space Grotesk, Montserrat, or custom).

When to use

  • When the user asks for a comprehensive, executive, or technical project report in PDF format.
  • To document and showcase historical evolution: from initial concept to solved challenges and architectural decisions (ADR/Decision Records).
  • To present a clear overview structured into chapters, milestones, and key takeaways for clients, stakeholders, investors, or the team.
  • When a polished layout is required, branded with project logo, colors, and modern typography (Space Grotesk, Montserrat).

When not to use

  • For short answers, quick notes, or simple inline markdown in chat.
  • To exclusively create presentation slides (use presentation or slide skills instead).
  • To extract isolated technical diagrams without narrative context (use archify or similar).

Procedure

  1. Historical Reconstruction & Project Analysis:
    • Inspect the entire repository: configuration files (package.json, hub.config.json, README), docs/, memory/, decision records (decision-record), and Git history (git log --reverse --oneline or thematic logs).
    • Extract the 5 narrative pillars:
      1. The Idea & Vision: the problem being solved, the context, the "why".
      2. Architecture & Technical Choices: stack, contracts, models, and dependencies.
      3. Milestones & Development: chronological timeline and intermediate goals achieved.
      4. Challenges & Solutions: technical hurdles, complex bugs, trade-offs, and how they were overcome.
      5. Current State & Roadmap: project status today and immediate next steps.
    • For detailed analysis guidance, see Reconstruction Guide.
  2. Asset Discovery & Brand Selection:
    • Check for brand kit in brand/brand-kit.json, brand/, ui/public/brand/, or repository assets.
    • Retrieve:
      • Logo: file path (SVG or PNG) or project mark.
      • Slogan / Tagline: identity statement of the project.
      • Color Palette: Primary, secondary, background, accent, and text colors.
      • Typography: Space Grotesk (modern tech, punchy geometric), Montserrat (elegant, versatile, clean), or project default (Inter, Plus Jakarta Sans).
    • For pairing details, see Typography and Brand Guide.
  3. Content Drafting with Editorial Hierarchy:
    • Organize the report into clearly numbered sections:
      • Cover Page: Logo, Project Title, Tagline, Version, Author/Team, Release Date.
      • Table of Contents: Navigable chapters and subchapters.
      • Executive Summary & Key Highlights: Highlight cards with bold for core concepts and italics for reflections and quotes.
      • Chapters 1–5: In-depth analysis with callout boxes for Problem Encountered (red/amber) and Solution Implemented (green/blue).
      • Milestone Timeline: Visual grid or table with dates, status (Completed, In Progress, Planned), and impact.
  4. HTML Composition (Dual-Mode Screen & Print Architecture):
    • Use the template in Report Template or include the essential CSS block:
      /* Print and PDF (A4 native with margins) */
      @page { size: A4 portrait; margin: 20mm 18mm 20mm 18mm; @bottom-right { content: "Page " counter(page); } }
      @page:first { margin: 0; @bottom-right { content: none; } }
      
      /* Screen and Browser preview (centered reader sheets, never edge-stuck) */
      @media screen {
        body { background-color: #0b132b; padding: 40px 20px; min-height: 100vh; }
        .cover-page, .chapter { max-width: 880px; margin: 0 auto 36px auto; border-radius: 12px; box-shadow: 0 16px 40px rgba(0,0,0,0.35); overflow: hidden; }
        .cover-page { height: auto; min-height: 860px; padding: 55px 48px; }
        .chapter { background: #ffffff; padding: 50px 48px; border: 1px solid var(--border-color); }
        .arch-diagram-card, .milestone-table { overflow-x: auto; }
      }
    • Save the HTML file in the designated destination (e.g. reports/<slug>-report.html or user-specified path).
  5. PDF Compilation via Skill Script:
    • Always run the skill's cross-platform Node.js script:
      node "<hub>/skills/own/report-pdf/scripts/generate-pdf.mjs" "<path_to_file.html>" "<path_to_file.pdf>"
    • Guarantee: generate-pdf.mjs automatically inspects the HTML file and injects the @media screen block if missing before compiling to PDF.
    • Verify that the generated PDF file exists, is readable, and has a non-zero file size.

Expected output

PDF report generated successfully!
- PDF file: <path/to/report.pdf> (<size>)
- HTML source: <path/to/report.html>
- Typography: Titles <Font>, Body <Font>
- Brand assets included: Logo, Color palette, Slogan
- Content: <N> chapters, <M> milestones, <K> challenges & solutions documented

Warnings

  • Mandatory Dual-Mode Screen / PDF rendering: HTML must never render edge-to-edge in a browser window. Always include the @media screen block with maximum width and centered margins (max-width: 880px; margin: 0 auto;), leaving @page rules intact for PDF rendering.
  • Source fidelity: Do not fabricate decisions, issues, or dates not grounded in real commits or documentation. Flag uncertainties clearly.
  • Page break controls: Ensure long tables and milestone blocks avoid splitting across pages via page-break-inside: avoid.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.